JOINT RECONSTRUCTION OF COMPRESSED MULTI-VIEW IMAGES

This paper proposes a distributed representation algorithm for multi-view images that are jointly reconstructed at the decoder. Compressed versions of each image are first obtained independently with random projections. The multiple images are then jointly reconstructed by the decoder, under the assumption that the correlation between images can be represented by local geometric transformations. We build on the compressed sensing framework and formulate the joint reconstruction as a l(2)-l(1) optimization problem. It tends to minimize the MSE distortion of the decoded images, under the constraint that these images have sparse and correlated representations over a structured dictionary of atoms. Simulation results with multi-view images demonstrate that our approach achieves better reconstruction results than independent decoding. Moreover, we show the advantage of structured dictionaries for capturing the geometrical correlation between multi-view images.